Browse Skills

A four-phase debugging framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting fixes. Use for any bug, test failure, or unexpected behavior.

Guides test-driven development by writing failing tests first, then implementing minimal code to pass them, and refactoring. Ensures tests verify actual behavior by enforcing the red-green-refactor cycle.

Prevents testing mock behavior, production pollution with test-only methods, and mocking without understanding dependencies. Use when writing or changing tests, adding mocks, or tempted to add test-only methods to production code.

Automates browser interaction to test and debug web applications using Playwright scripts. Ideal for building features or troubleshooting front-end issues with real browser testing.

Guides developers through reviewing public API changes in the Fluid Framework, including release tag assignment, breaking change classification, API Council requirements, deprecation process, and changeset guidance.

Provides title style options (Conventional Commits or plain imperative), body template based on the repository's pull request template, and CI requirements for composing, drafting, or reviewing PRs in the Fluid Framework repository.

Guides the creation of pull requests for the Fluid Framework project, ensuring branch safety, composing titles and descriptions per convention, and opening PRs after user confirmation.

Performs multi-level code review on recent changes, checking syntax, security, performance, and spec compliance. Offers to automatically apply findings via the fix gate that triggers planning and dispatch.

Runs L1-L5 audits against a PR's diff, posts findings as a batched inline or summary review, provides a fix chain for needed changes, and optionally merges approved PRs.

Systematic root-cause analysis for bugs, test failures, runtime errors, and broken builds. Use before patching to identify structural causes, not symptoms, with a step-by-step agent workflow.

Performs multi-level code reviews (from syntax checks to adversarial probing) on diffs, commits, branches, or PRs, with mandatory security scanning at higher levels. Findings are written to .hyperflow/audits/ and a fix-gate can route fixes to planning.

Runs pre-commit verification gates (type generation, linting, typecheck, tests, build, i18n) on changed files, fixes simple issues, and commits with a conventional commit message when all gates pass. Ideal after completing a task or making code changes.